© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 53753
    Prev
    Next
    INDEX
    Explanations

    semicolons in the document

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ãģªãģĮãĤī
    -0.07
     Returning
    -0.06
    iesz
    -0.06
    .cum
    -0.06
    evice
    -0.06
     ?><?
    -0.06
    .species
    -0.06
    á»ĭ
    -0.06
    azzi
    -0.06
    okt
    -0.06
    POSITIVE LOGITS
    ãi
    0.07
    wand
    0.07
    ENU
    0.07
     excer
    0.06
    à¥įà¤ķर
    0.06
    иÑĤÑĥ
    0.06
    959
    0.06
    âĢĮâĢĮ
    0.06
    ëŀij
    0.06
    949
    0.06
    Activations Density 0.007%

    No Known Activations